Wind turbine blade inspection system and method based on unmanned aerial vehicle

A wind turbine blade inspection system based on an unmanned aerial vehicle, comprising:

• a processor, a camera, an infrared thermal imager, and a sensor, wherein,
• the camera, the infrared thermal imager, and the sensor are used for collecting blade data and surrounding environment data of blades to be inspected,
• and wherein the processor is used for determining feature inspection points of the unmanned aerial vehicle according to the blade data and the surrounding environment data, and generating inspection paths based on the feature inspection points;
• the camera is used for shooting corresponding blade at the feature inspection points according to the inspection paths to obtain a first inspection image and a second inspection image;
• the processor is further used for receiving the first inspection image and the second inspection image, analyzing the first inspection image and the second inspection image to obtain a health state of the corresponding blade, and making a maintenance plan according to the health state of each of the blades;
• wherein the collecting blade data and surrounding environment data of blades to be inspected comprises:
• the blade data comprises a hub height and a blade tip radius of each of the blades to be inspected, a first blade space coordinate system is established according to the hub height and a hub center point, and a first rotating area of each of the blades to be inspected is determined according to the blade tip radius;
• the surrounding environment data comprises wind speed data, weather data and obstacle data, an instantaneous wind speed is determined according to the wind speed data, first correction is performed on the first rotating area according to the instantaneous wind speed, a weather condition in a preset period is predicted according to the weather data, and an obstructed frequency corresponding each of the blades to be inspected is determined according to the obstacle data;
• second correction is performed on the first rotating area according to the weather condition and the obstructed frequency, to obtain a target rotating area;
• wherein the first correction being performed on the first rotating area according to the instantaneous wind speed comprises:
• historical wind speed data is obtained, a historical wind speed-rotating area mapping table is determined according to the historical wind speed data, a first historical wind speed is determined according to the first rotating area, the first historical wind speed is compared with current instantaneous wind speed, if the instantaneous wind speed is not greater than the first historical wind speed, a first correction coefficient is selected to perform first correction on the first rotating area, and if the instantaneous wind speed is greater than the first historical wind speed, an instantaneous rotating area corresponding to the instantaneous wind speed in the historical wind speed-rotating area mapping table is determined, an area difference value between the instantaneous rotating area and the first rotating area is calculated, a wind speed difference value between the instantaneous wind speed and the first historical wind speed is calculated, a second correction coefficient is determined according to a ratio of the wind speed difference value to the area difference value, and first correction is performed on the first rotating area according to the second correction coefficient;
• wherein second correction being performed on the first rotating area according to the weather condition and the obstructed frequency comprises:
• a historical weather-rotating area mapping table is determined according to the weather data, a corresponding weather rotating area is determined according to predicted weather condition, and a weather weight coefficient is determined according to predicted probability value of weather condition and the weather rotating area;
• a historical obstacle-rotating area mapping table is determined according to the obstacle data, and the obstructed frequency of current each of the blades to be inspected in a preset time period is determined;
• if the obstructed frequency is greater than a preset obstacle frequency, a plurality of rotating areas corresponding to historical obstacle in a preset time period are determined based on the historical obstacle-rotating area mapping table, a rotating area average value is calculated, and an obstacle weight coefficient is determined according to the rotating area average value and the obstructed frequency;
• a third correction coefficient is determined according to the weather weight coefficient and the obstacle weight coefficient, and second correction is performed on the first rotating area according to the third correction coefficient to obtain the target rotating area;
• wherein determining feature inspection points of the unmanned aerial vehicle according to the blade data and the surrounding environment data comprises:
• a plurality of first inspection points and a plurality of second inspection points of the unmanned aerial vehicle are determined on the first blade space coordinate system based on the target rotating area of each of the blades to be inspected, wherein the first inspection points and the second inspection points are respectively arranged at two sides of each of the blades to be inspected, and the first inspection points and the second inspection points are set at a preset shooting inclination angle;
• inspection images of the plurality of first inspection points and the second inspection points are obtained, preprocessing is performed on the inspection images, recognition rate and accuracy rate of feature positions in preprocessed inspection images are obtained, and a first feature shooting inclination angle and a second feature shooting inclination angle are determined according to the recognition rate and accuracy rate;
• a first inspection point corresponding to the first feature shooting inclination angle is set as a first feature inspection point, and a second inspection point corresponding to the second feature shooting inclination angle is set as a second feature inspection point.